Convert M3U to JSON — Export IPTV Playlist as Structured Data

[
  {
    "title": "BBC One HD",
    "url": "http://provider.example.com/live/user/pass/101.ts",
    "duration": -1,
    "tvgId": "bbc.one.uk",
    "tvgName": "BBC One",
    "tvgLogo": "https://logos.example.com/bbc1.png",
    "groupTitle": "UK | Entertainment"
  },
  {
    "title": "Sky Sports Main",
    "url": "http://provider.example.com/live/user/pass/201.ts",
    "duration": -1,
    "tvgId": "sky.sports.main",
    "tvgName": "Sky Sports Main",
    "tvgLogo": "https://logos.example.com/skysports.png",
    "groupTitle": "UK | Sports"
  }
]

function parseM3U(text) {
  const lines = text.split(/\r?\n/);
  const entries = [];
  let pending = null;

  for (const line of lines) {
    const trimmed = line.trim();
    if (!trimmed) continue;

    if (trimmed.startsWith('#EXTINF')) {
      const durationMatch = trimmed.match(/#EXTINF:([-\d.]+)/);
      const titleMatch = trimmed.match(/,(.+)$/);
      const attrMatch = (attr) => {
        const m = trimmed.match(new RegExp(`${attr}="([^"]*)"`, 'i'));
        return m ? m[1] : '';
      };

      pending = {
        duration: durationMatch ? parseFloat(durationMatch[1]) : -1,
        title: titleMatch ? titleMatch[1].trim() : '',
        tvgId: attrMatch('tvg-id'),
        tvgName: attrMatch('tvg-name'),
        tvgLogo: attrMatch('tvg-logo'),
        groupTitle: attrMatch('group-title'),
      };
    } else if (!trimmed.startsWith('#') && pending) {
      entries.push({ ...pending, url: trimmed });
      pending = null;
    }
  }
  return entries;
}

// Usage:
const json = JSON.stringify(parseM3U(m3uText), null, 2);

import re
import json

def parse_m3u(text):
    entries = []
    pending = None
    
    for line in text.splitlines():
        line = line.strip()
        if not line:
            continue
        
        if line.startswith('#EXTINF'):
            duration_match = re.search(r'#EXTINF:([-\d.]+)', line)
            title_match = re.search(r',(.+)$', line)
            
            def get_attr(attr):
                m = re.search(rf'{attr}="([^"]*)"', line, re.IGNORECASE)
                return m.group(1) if m else ''
            
            pending = {
                'duration': float(duration_match.group(1)) if duration_match else -1,
                'title': title_match.group(1).strip() if title_match else '',
                'tvg_id': get_attr('tvg-id'),
                'tvg_name': get_attr('tvg-name'),
                'tvg_logo': get_attr('tvg-logo'),
                'group_title': get_attr('group-title'),
            }
        elif not line.startswith('#') and pending:
            pending['url'] = line
            entries.append(pending)
            pending = None
    
    return entries

# Usage:
with open('playlist.m3u', 'r', encoding='utf-8') as f:
    data = parse_m3u(f.read())

with open('channels.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, indent=2, ensure_ascii=False)